mirror of
https://github.com/deepseek-ai/deepseek-harness.git
synced 2026-08-29 04:26:38 +00:00
docs: rescan rebased documentation hierarchy
This commit is contained in:
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write apps/cli/reference/README.md
|
||||
README.md: 6c83dd8312cf797614b03e8632b72fd1133577d3
|
||||
README.zh.md: 00016ebc2f2cffa489072695cdc280ed2d875145
|
||||
README.md: b37ec9ed61ea4e9899a51316065d4188f30997ad
|
||||
README.zh.md: ca29808a6c8e670f0d0b82c59b1a2c1fa0e13565
|
||||
|
||||
@@ -2,81 +2,75 @@
|
||||
|
||||
English | [中文](README.zh.md)
|
||||
|
||||
Argv is parsed once through a [Commander](https://github.com/tj/commander.js) adapter ([`src/args.ts`](../src/args.ts)): one program whose default (no subcommand) is the TUI/headless surface (`--config`, `-p`/`--prompt`, `--resume`, `--dump-config`, `--dump-default-config`), whose `meta` subcommand is the same TUI over this checkout, whose `upgrade` subcommand is a guided-session entry, and whose `web` subcommand is the browser UI. `meta` and `upgrade` are experimental: each runs only with its `--experimental` flag or with `DSH_EXPERIMENTAL=1` in the environment, and fails loud (stderr, exit 1) otherwise. `src/bin.ts` switches on the resolved mode and dynamic-imports only that mode's module. `dsh --help` lists every mode and `dsh web --help` renders the web usage, `dsh --version` prints this app's version, and an unknown option or a mistyped `--resume` fails loud (stderr, exit 1) instead of misrouting. Every subcommand that shares no option with the default surface — `upgrade`, `web`, `meta` — rejects a leaked `--config`/`-p`/`--resume`/dump flag rather than running and dropping it. `dsh web`'s `--host`/`--port` are unvalidated pass-through overrides: the `dsh-host-webserver` schema is the single source of both the default (the shipped Web overlay value when a flag is absent) and validity, and rejects a bad value at boot. `--trusted-host` appends named authorities for the /api browser-trust fence; an all-interfaces bind additionally derives the machine's LAN IP literals itself ([`src/app-cli-entry.ts`](../src/app-cli-entry.ts)), so the printed LAN URL works without flags.
|
||||
This reference defines the raw-config, Web, and headless command modes. Argv is parsed once through [`src/args.ts`](../src/args.ts), and [`src/bin.ts`](../src/bin.ts) dynamically imports only the selected runner.
|
||||
|
||||
The TUI surface:
|
||||
## Raw config
|
||||
|
||||
- boots `base.cordis.yml` plus `tui.cordis.yml` through [`dsh-app-boot`](../../../packages/ui/app-boot/README.md); `--config <path>` applies a patch-list overlay instead of the personal overlay, while `--config-replace <path>` boots that file as the complete tree;
|
||||
- resumes a persisted session with `dsh --resume <session-id>` and, when the Node host exposes `process.execve`, supplies the TUI's in-place handoff host: after selector preflight and current-session flush, the host disposes the app and replaces the process with a normalized resume invocation; runtimes without process replacement leave the session running and say so. This CLI owns session identity and the exit line rather than the config: it mints or selects the `main` session id and provides it, plus the exact command that reproduces this invocation, on the boot context ([`MAIN_SESSION_ID_KEY`](../../../packages/ui/tui/README.md) and `TUI_GOODBYE_MESSAGE_KEY`). No `cordis.yml` key can drop resume, and a missing or unreadable id fails loud instead of creating a fresh session;
|
||||
- treats the **invoking directory** as the workspace — sessions, relative paths, and workspace instructions resolve from the cwd (`dsh meta` is the sole exception, below);
|
||||
- tells the agent where its own source lives: after boot it adds a prompt section naming this harness checkout, resolved from the launcher's real path so it holds under a PATH symlink and an arbitrary cwd, so the self-referential `cordis` toolset can read and modify it;
|
||||
- applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../../packages/ui/app-boot/README.md#personal-config)): `config.yaml` patches the booted tree, while `.env` there is the credential provider's own store (never hoisted into the environment, so keys stay rotatable). Environment precedence is ambient > project `.env`. The shipped tree's Cordis HMR keeps `config.yaml` live; an explicit `--config` tree replaces that overlay, and a tree without HMR reads it at startup only.
|
||||
- presents the [versioned first-run welcome](../../../.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md) through the mounted TUI overlay service when its immutable marker is absent under `DSH_HOME`; only Enter creates that version's marker, while Escape, disposal, or process exit leaves it eligible. The official DeepSeek icon, responsive terminal rasters, all-locale Chinese copy, and notice version are static local owners; the overlay never writes a session event or model context.
|
||||
- registers bare `/compact`: while the agent is idle, it summarizes useful older history even below automatic pressure, rejects arguments, and reports success only after the standalone replacement bracket is durable. A prompt submitted during compaction keeps its queue identity and starts after that checkpoint; injected context remains visible.
|
||||
|
||||
`dsh meta` is that same TUI with this harness checkout as the workspace, so working on dsh itself needs no `cd`. It chdirs to the checkout root — resolved from the launcher's real path, the same root the source-path prompt section names — after the environment is settled, so precedence is unchanged while the session cwd and HMR watch root move together. Meta always starts a fresh session and accepts no default-surface options; use ordinary `dsh --resume <id>` to resume a persisted session.
|
||||
|
||||
`dsh upgrade` is a guided fresh-session entry over the default TUI surface: it mints a fresh session in the invoking directory and seeds its first turn with the bundled `dsh-upgrade` skill, exactly as if the user typed `/skill:<name>`. The launcher passes the skill name on the boot context ([`INITIAL_SKILL_KEY`](../../../packages/ui/tui/README.md)), which the TUI auto-invokes once the chat is live. The command takes no options beyond the experimental gate — `--config`, `-p`, and `--resume` fail loud — and seeds only on this first launch, so a later `dsh --resume <id>` of the session is an ordinary TUI session with no re-injection.
|
||||
|
||||
`dsh --dump-config` and `dsh web --dump-config` print the composed config tree — the shipped base, the surface overlay, and the `--config` or personal overlay, exactly the layers that surface would boot — as YAML on stdout and exit without booting; `--dump-default-config` stops at the surface overlay, so diffing the two shows precisely what the user layer changes. Each run of rows is preceded by a `# ==` comment naming the file it comes from and the layers that patched it (e.g. `# == base.cordis.yml, patched by tui.cordis.yml`), so the output shows provenance while staying one loadable document. Composition runs through the include's own patch algorithm and YAML dialect (`applyEntryPatches`/`entryListSchema` from `@cordisjs/plugin-include`), so the dump cannot drift from what boots; `!!js` expressions print verbatim and unevaluated, and a patch whose target row is absent is reported on stderr with its layer, mirroring the Loader's boot-time warning. Launcher-owned boot-context values (session identity, CLI-flag patches) are per-invocation facts outside the config tree and do not appear. The dump flags reject boot-only flags (`-p`, `--resume`, `--config-replace`) rather than silently ignoring them, and `--dump-default-config` takes no `--config`.
|
||||
|
||||
The Web and headless surfaces boot `base.cordis.yml` plus `web.cordis.yml`, then apply `$DSH_HOME/config.yaml`; an explicit `--config <path>` replaces that personal overlay. Both surfaces otherwise share the same composition: both tell the coding agent its resolved model and session working directory, treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root <path>` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, opt into first-message model titles, use the same bounded transient model-request retry policy as the TUI, and mount a disposable in-memory SQLite content-index service. Web additionally names the DeepSeek Harness Web GUI as the interaction surface, this checkout as its own source location, and the process's canonical local URL and mode in both the prompt and managed `$DSH_WEB_URL`/`$DSH_WEB_MODE`; references such as “this page” therefore identify the GUI without claiming access to implicit DOM, route, or screenshot state. In production mode the host reads rebuilt frontend dist and client bundles on the next request, so refreshing the existing URL updates that GUI without replacing its process. `dsh web --dev` mounts the client-plugin HMR receiver, but no-refresh updates additionally require `pnpm run dev:web` in the same checkout to watch and rebuild plugin bundles; shell and ordinary package changes still require a rebuild and page refresh. Bare `apps/web` Vite serving fails before listening because it cannot inject `window.__DSH_BOOT__`. The index service is ACTIVE at boot, while its `node:sqlite` module and database handle open only on the first content search. This keeps Node 22 startup output free of SQLite's experimental warning before search is used; the first actual search may still emit the runtime warning. Each service instance owns its database, so parallel invocations neither share unsupported SQLite state nor leave derived index files behind, and the first search lazily reconciles live and persisted logs. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`).
|
||||
|
||||
The shared composition defaults new TUI, Web, and headless sessions to the `workspace-write` permission preset (`workspace-write` file mode plus `ask` approval policy). Sandbox-enforced bash and filesystem mutations may write only under the session workspace and platform temporary roots; reads, network access, and process visibility are not confined. The browser answers one-shot approval requests and exposes the Access picker; the TUI exposes `/permission`, but has no approval-request answerer, so an automatic wider retry there fails closed until the user deliberately changes the session preset. `DSH_PERMISSION_MODE` changes the process fallback, while a stored General-settings Permission value applies to later sessions without changing an open one.
|
||||
|
||||
All three surfaces consume `$DSH_HOME/config.yaml`; the TUI and Web apply valid edits live, while one-shot headless runs read it at startup. The shipped trees include an empty `repository-plugins` row, so a standalone user can add prepared GitHub Plugins without an SDK project or install command:
|
||||
|
||||
```yaml
|
||||
- id: repository-plugins
|
||||
name: '@deepseek-ai/dsh-repository-plugin'
|
||||
config:
|
||||
repositories:
|
||||
- 'github:PolyArch/humanize#<commit>'
|
||||
```
|
||||
|
||||
The repository must contain a prepared `.dsh-plugin` package; the [repository Plugin contract](../../../packages/cordis/repository-plugin/README.md#standalone-app-configuration) documents authoring, nested Plugin paths, the immutable cache, trust boundary, and failure semantics. A failed live edit keeps the last good tree and emits Cordis's `hmr/config-update-failed` event.
|
||||
|
||||
The shipped TUI and Web compositions register the native DeepSeek adapter plus pi-ai OpenAI and Anthropic profiles. Credentials and endpoint overrides come from the provider-standard `DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`, `OPENAI_API_KEY` / `OPENAI_BASE_URL`, and `ANTHROPIC_API_KEY` / `ANTHROPIC_BASE_URL` pairs in the boot's layered environment.
|
||||
|
||||
Every surface also registers `web_search` and only `web_search`. Search uses DeepSeek's Anthropic-compatible Messages endpoint, resolves the same `DEEPSEEK_API_KEY` reference for every call, and accepts the separate `DEEPSEEK_SEARCH_BASE_URL` endpoint override; each search is an auxiliary model request with its own latency and token cost. `web_fetch` remains disabled and the composition mounts no default fetch provider, so deployments that need arbitrary page retrieval must opt in through an overlay. The deployment decision and its security boundary live in the [default Web search Agent Note](../../../.agents/notes/implemented/feature/2026-07-31-web-default-search.md).
|
||||
|
||||
`DSH_TOOLS_MODE` selects the tool presentation mode for the whole Web/headless process: `native` (the schema default when unset), `code` (the `run_code`-only Code Mode wire), or `both`; any other value fails loud at boot through the `dsh-tools` config schema. The setting is process-wide because Loader composition is static. The TUI surface ignores it and pins `native`.
|
||||
|
||||
[`core-web.cordis.yml`](../config/core-web.cordis.yml) is an opt-in `dsh web --config` overlay that keeps the shipped Web host, browser, Workspace, persistence, and permission composition while reducing the default native model surface to owner-scoped persistent `bash` and `str_replace_editor`. The PTY backend and editor consume the existing Web sandbox and filesystem providers. An open persistent shell prevents changing that session's permission mode until the shell closes, so a shell created under wider access cannot survive a downgrade. `DSH_TOOLS_MODE` still controls native/Code Mode presentation for the resulting two-tool registry.
|
||||
|
||||
From a source checkout, start this minimal Web profile with:
|
||||
Raw `dsh` requires an explicit patch-list config:
|
||||
|
||||
```sh
|
||||
pnpm run dsh web --config apps/cli/config/core-web.cordis.yml
|
||||
dsh --config ./app.cordis.yml
|
||||
```
|
||||
|
||||
Every `dsh` surface — TUI, Web, and headless — reports session telemetry by default (the row lives in the shared `base.cordis.yml`): every session-log event streams as OTLP/HTTP log records to `https://harness-telemetry.deepseeksvc.com/v1/logs` on a 10-second batch cadence. `DSH_TELEMETRY_OTLP_URL` points the exporter at a different collector; setting `DSH_TELEMETRY_DISABLED` to ANY non-empty value — including `0` or `false` — disables the row before it loads (a privacy switch prefers off-by-mistake over on-by-mistake). No redaction rule is mounted in this composition yet: exported records are the raw captured copy, including message text, tool arguments and results, and the session's working-directory path. The deployment rulings live in the [web-telemetry-default-mount Agent Note](../../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md).
|
||||
The named file is applied directly over [`config/base.cordis.yml`](../config/base.cordis.yml) through the Include plugin's patch algorithm. It is not a complete replacement tree, and neither the personal `$DSH_HOME/config.yaml` nor another surface overlay is added. The base deliberately contains no startup agent or interaction front door; the required overlay selects those deployment details. Relative config paths resolve from the invoking directory. A parse, schema, resolution, or plugin boot failure is reported and exits nonzero. SIGINT and SIGTERM dispose the mounted root before exit.
|
||||
|
||||
MCP servers are not a shipped default, because a default would have to name one: `@deepseek-ai/dsh-mcp-client` mounts exactly one server per row and spawns it as a child process, outside `ctx.bash` and so outside the sandbox policy. The package is a runtime dependency of this CLI, so an installed `dsh` can mount your own servers from `$DSH_HOME/config.yaml` or a `--config` overlay without a source checkout:
|
||||
A patch targets a base row by `id` and replaces that row's complete `config` value rather than deep-merging keys. Patch lists may also insert new rows whose plugin modules the shipped Loader can resolve:
|
||||
|
||||
```yaml
|
||||
- insert:
|
||||
- id: mcp-github
|
||||
name: '@deepseek-ai/dsh-mcp-client'
|
||||
config:
|
||||
serverName: github
|
||||
transport: stdio
|
||||
command: npx
|
||||
args: ['-y', '@modelcontextprotocol/server-github']
|
||||
env:
|
||||
GITHUB_TOKEN: !!js process.env.GITHUB_TOKEN
|
||||
- id: agent-loop
|
||||
config:
|
||||
agents:
|
||||
- id: main
|
||||
provider: deepseek-official
|
||||
model: deepseek-v4-flash
|
||||
```
|
||||
|
||||
The model then sees `mcp__github__*`. See the [mcp-client README](../../../packages/mcp/mcp-client/README.md) for the Streamable HTTP transport and the full field table.
|
||||
Inspect the effective tree without booting it:
|
||||
|
||||
## Install (developer machine)
|
||||
```sh
|
||||
dsh --dump-default-config
|
||||
dsh --config ./app.cordis.yml --dump-config
|
||||
```
|
||||
|
||||
Symlink the source-running launcher onto your PATH; it resolves the checkout through its own real path, so code changes apply on the next launch with no build step:
|
||||
`--dump-default-config` prints only the shipped base. `--dump-config` requires `--config` and prints base plus overlay with provenance comments. Composition uses `applyEntryPatches` and `entryListSchema` from `@cordisjs/plugin-include`; `!!js` expressions remain unevaluated, and unmatched patch targets are reported on stderr.
|
||||
|
||||
## Web and headless
|
||||
|
||||
`dsh web` boots `base.cordis.yml` plus [`config/web.cordis.yml`](../config/web.cordis.yml), followed by `$DSH_HOME/config.yaml` when present. `dsh web --config <path>` replaces that personal layer with the explicit patch list. `--host`, `--port`, `--workspace-root`, and repeatable `--trusted-host` values become Web host patches; their owning plugin schemas validate them at boot. `--dev` mounts the client-plugin HMR receiver and expects a separate `pnpm run dev:web` watcher for no-refresh client bundle updates.
|
||||
|
||||
```sh
|
||||
dsh web
|
||||
dsh web --config ./web-profile.cordis.yml
|
||||
dsh web --dump-default-config
|
||||
dsh web --dump-config
|
||||
```
|
||||
|
||||
The production Web runner needs built package and frontend artifacts (`pnpm run build`). It serves `http://127.0.0.1:3080` by default. Binding all interfaces also trusts the machine's discovered LAN IP literals; `--trusted-host` adds named authorities accepted by the `/api` browser-trust fence.
|
||||
|
||||
`dsh -p "task"` uses the same base and Web composition with the startup personal config, starts its Web host on an OS-assigned port, runs one fresh persisted session, prints the final answer, and exits. It accepts neither `--config` nor raw config-dump flags.
|
||||
|
||||
Web and headless process shutdown gives the plugin tree up to five seconds to dispose. The first `SIGINT`/`SIGTERM` starts that graceful drain; a second signal forces immediate exit. If headless normal completion is already stuck in disposal, the first `Ctrl+C` is the escalation and exits immediately instead of being swallowed.
|
||||
|
||||
Both modes treat the invoking directory as the default workspace root, load applicable `AGENTS.md` or `CLAUDE.md` instructions with a 65,536-byte render budget, and use an in-memory SQLite session content index. Web watches valid personal config edits; headless reads the file once at startup. The [app-boot personal-config contract](../../../packages/ui/app-boot/README.md#personal-config) owns layer precedence, credential storage, live-update failure behavior, and `$DSH_HOME` resolution.
|
||||
|
||||
New sessions default to the `workspace-write` permission preset. Bash and filesystem mutations are restricted to the session workspace and platform temporary roots; reads, network access, and process visibility are not confined. `DSH_PERMISSION_MODE` changes the process fallback. Stored General-settings permissions affect later Web sessions, not an already-open one.
|
||||
|
||||
`DSH_TOOLS_MODE` selects `native`, `code`, or `both` for the Web/headless process; another value fails at boot. [`config/core-web.cordis.yml`](../config/core-web.cordis.yml) is an optional Web overlay that reduces the native model surface to persistent `bash` and `str_replace_editor` while retaining the shipped host, browser, workspace, persistence, and permission composition.
|
||||
|
||||
## Shared deployment behavior
|
||||
|
||||
The base mounts the native DeepSeek adapter, settings and credential providers, stable `web_search`, repository Plugin support, and session telemetry. Provider credentials live in `$DSH_HOME/.env` or the ambient environment and remain rotatable because the launcher never hoists the credential file into `process.env`. Search uses `DEEPSEEK_API_KEY` and accepts `DEEPSEEK_SEARCH_BASE_URL`; `web_fetch` is disabled unless an overlay inserts a provider and enables it.
|
||||
|
||||
Session events stream as OTLP/HTTP logs by default. `DSH_TELEMETRY_OTLP_URL` selects another collector. Any non-empty `DSH_TELEMETRY_DISABLED` disables the telemetry row before boot. The shipped base has no telemetry redaction rule, so exported records can contain message text, tool arguments and results, and workspace paths; the [telemetry Agent Note](../../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md) owns that deployment decision.
|
||||
|
||||
The empty `repository-plugins` row lets Web/headless personal config and raw overlays mount prepared immutable repository Plugin generations. See the [repository Plugin contract](../../../packages/cordis/repository-plugin/README.md#standalone-app-configuration). The CLI also ships `@deepseek-ai/dsh-mcp-client` as a dependency for overlays, but no MCP server is enabled by default because each server command is trusted executable code outside the agent sandbox.
|
||||
|
||||
## Source launcher
|
||||
|
||||
Link the source-running launcher onto PATH:
|
||||
|
||||
```sh
|
||||
ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh
|
||||
```
|
||||
|
||||
Source launches run `apps/cli/src/bin.ts` through tsx's ESM-only hook (`node --import tsx/esm`), which transforms TypeScript and projects the root tsconfig `paths` map into module resolution. Node's native TypeScript modes are not used: Node 26 removed `--experimental-transform-types`, and strip-only mode rejects syntax the source graph relies on (vendored parameter properties, decorators, runtime enums/namespaces). The CJS hook stays off because the source graph is ESM-only and the CJS resolver adds ~0.4s of startup. `bin/dsh` pins `TSX_TSCONFIG_PATH` to the checkout's root tsconfig so resolution is cwd-independent, and the `dsh-source-launch-smoke` node-compat gate runs this exact launch vector on every supported Node line. tsx applies the `paths` map without checking dependency declarations, so declaration completeness rests on the static gates: the TUI configs resolve bare plugins through `examples/package.json`, the Web/headless `cordis.yml` through this package's `dependencies`, and `verify-cordis-config` requires every configured bare plugin to be declared, while allowing unrelated dependencies.
|
||||
|
||||
`pnpm run dsh` runs the same entry from the repo root and forwards arguments directly, for example `pnpm run dsh -p "task"`. The built form (`lib/bin.js`, via `pnpm run build`) boots the same config under plain Node.
|
||||
It resolves the checkout through its real path and launches `apps/cli/src/bin.ts` with `node --import tsx/esm`. `TSX_TSCONFIG_PATH` is pinned to the checkout root, so workspace package resolution is independent of the invoking directory. `pnpm run dsh` uses the same entry and forwards arguments. The built form is `apps/cli/lib/bin.js` after `pnpm run build`.
|
||||
|
||||
@@ -2,81 +2,75 @@
|
||||
|
||||
[English](README.md) | 中文
|
||||
|
||||
Argv 只会通过 [Commander](https://github.com/tj/commander.js) 适配器([`src/args.ts`](../src/args.ts))解析一次:同一个程序的默认形式(无子命令)是 TUI/无头界面(`--config`、`-p`/`--prompt`、`--resume`、`--dump-config`、`--dump-default-config`),`meta` 子命令是以本 checkout 为 workspace 的同一个 TUI,`upgrade` 子命令是引导会话入口,`web` 子命令则是浏览器 UI。`meta` 与 `upgrade` 是实验性命令:只有带上各自的 `--experimental` 标志或在环境中设置 `DSH_EXPERIMENTAL=1` 才会运行,否则明确报错(stderr,退出码 1)。`src/bin.ts` 按解析后的 mode 分支,仅动态导入该 mode 的模块。`dsh --help` 列出所有 mode,`dsh web --help` 渲染 Web 用法,`dsh --version` 打印此应用的版本;未知选项或拼错的 `--resume` 会明确报错(stderr,退出码 1),而不会被错路由。凡与默认界面不共享任何选项的子命令(`upgrade`、`web`、`meta`)都会拒绝泄漏进来的 `--config`/`-p`/`--resume`/dump 标志,而不会照常运行并丢弃它。`dsh web` 的 `--host`/`--port` 是未验证的直通覆盖:`dsh-host-webserver` schema 是默认值(标志缺失时使用已交付的 Web 覆盖层值)和有效性的唯一真源,并在启动时拒绝错误值。`--trusted-host` 为 /api 浏览器信任栅栏追加具名权威;全接口绑定还会自行推导本机的 LAN IP 字面量([`src/app-cli-entry.ts`](../src/app-cli-entry.ts)),因此打印出的 LAN URL 无需任何标志即可使用。
|
||||
本参考定义原始配置、Web 和无头命令模式。参数由 [`src/args.ts`](../src/args.ts) 统一解析,[`src/bin.ts`](../src/bin.ts) 只动态导入选中的运行器。
|
||||
|
||||
TUI 界面:
|
||||
## 原始配置
|
||||
|
||||
- 通过 [`dsh-app-boot`](../../../packages/ui/app-boot/README.md) 启动 `base.cordis.yml` 与 `tui.cordis.yml`;`--config <path>` 应用一个补丁列表覆盖并替代个人覆盖,而 `--config-replace <path>` 将指定文件作为完整配置树启动;
|
||||
- 使用 `dsh --resume <session-id>` 恢复已持久化会话。当 Node 宿主公开 `process.execve` 时,还会提供 TUI 的原地移交宿主:选择器预检并刷新当前会话后,宿主会对应用执行 dispose(资源释放),并以规范化的恢复调用替换进程;不支持进程替换的运行时会让会话继续运行并给出提示。会话身份与退出行由本 CLI 拥有,而非由配置指定:它创建或选定 `main` 会话 id,并把该 id 以及可复现本次调用的确切命令一起提供到启动上下文([`MAIN_SESSION_ID_KEY`](../../../packages/ui/tui/README.md) 与 `TUI_GOODBYE_MESSAGE_KEY`)。任何 `cordis.yml` 键都无法移除恢复能力;缺失或无法读取的 id 会明确报错,而不会创建新会话;
|
||||
- 将 **调用目录** 视为 workspace:会话、相对路径和 workspace 指令都从 cwd 解析(`dsh meta` 是唯一例外,见下文);
|
||||
- 告知 agent(智能体)自身源码所在位置:启动后添加一个命名此 harness checkout 的提示词段。该路径从启动器的真实路径解析,因此在 PATH 符号链接和任意 cwd 下仍然有效,使自指的 `cordis` 工具集可以读取并修改它;
|
||||
- 应用 `~/.dsh` 中的个人覆盖(参见 [app-boot 的个人配置](../../../packages/ui/app-boot/README.md#personal-config)):`config.yaml` 修补已启动的树,而那里的 `.env` 是凭据提供方自己的存储(绝不会被提升进环境,因此密钥始终可轮换)。环境优先级为环境中已有的值 > 项目 `.env`。已交付配置树中的 Cordis HMR(热模块替换)会持续应用 `config.yaml` 的变更;显式 `--config` 配置树会替代该个人覆盖,未包含 HMR 的配置树只在启动时读取该文件。
|
||||
- 当 `DSH_HOME` 下不存在不可变确认标记时,通过已挂载的 TUI overlay 服务呈现[版本化首次运行欢迎页](../../../.agents/notes/implemented/feature/2026-07-30-versioned-tui-first-run-welcome.md);只有 Enter 会创建该版本的标记,Escape、资源释放或进程退出仍保留展示资格。官方 DeepSeek 图标、响应式终端栅格图、所有 locale 共用的中文文案和通知版本均由静态本地文件持有;overlay 不会写入会话事件或模型上下文。
|
||||
- 注册裸 `/compact`:agent 空闲时,即使未达到自动压力,也会摘要有效的较早历史;该命令拒绝参数,并只在独立替换标记对持久化后报告成功。压缩(compaction)期间提交的提示词保留其队列身份,并在该检查点之后启动;注入的上下文仍保持可见。
|
||||
|
||||
`dsh meta` 是以本 harness checkout 为 workspace 的同一个 TUI,因此开发 dsh 自身无需 `cd`。它在环境确定之后才 chdir 到 checkout 根目录(从启动器的真实路径解析,与源码路径提示词段所指的根目录相同),因此环境优先级不变,而会话 cwd 与 HMR 监视根目录会一并移动。Meta 始终创建新会话,不接受默认界面的任何选项;恢复已持久化会话应使用普通的 `dsh --resume <id>`。
|
||||
|
||||
`dsh upgrade` 是默认 TUI 界面之上的引导式全新会话入口:它在调用目录中创建一个全新会话,并以内置 `dsh-upgrade` skill(技能)播种其首轮,效果等同于用户手动键入 `/skill:<name>`。启动器将 skill 名称提供到启动上下文([`INITIAL_SKILL_KEY`](../../../packages/ui/tui/README.md)),TUI 在聊天就绪后自动调用它。该命令除实验性门槛外不接受任何选项——`--config`、`-p`、`--resume` 都会明确报错——且仅在首次启动时播种,因此之后 `dsh --resume <id>` 恢复该会话时是普通 TUI 会话,不会重复注入。
|
||||
|
||||
`dsh --dump-config` 和 `dsh web --dump-config` 把合成后的配置树——已交付的基础配置、界面覆盖层,以及 `--config` 或个人覆盖层,恰好是该界面启动时组装的那些层——以 YAML 打印到 stdout 后退出,不启动任何东西;`--dump-default-config` 止步于界面覆盖层,因此对两份输出做 diff 就能精确看出用户层改了什么。每段连续的行之前都有一条 `# ==` 注释,标明该段来自哪个文件以及被哪些层修补过(例如 `# == base.cordis.yml, patched by tui.cordis.yml`),因此输出既展示来源,又仍是一份可加载的文档。合成通过 include 自己的补丁算法和 YAML 方言(`@cordisjs/plugin-include` 的 `applyEntryPatches`/`entryListSchema`)完成,因此 dump 不可能与实际启动漂移;`!!js` 表达式原样打印、不求值,目标行不存在的补丁会连同其所在层报到 stderr,与 Loader 启动时的警告一致。由启动器持有的启动上下文值(会话身份、CLI 标志补丁)是每次调用的事实,位于配置树之外,不会出现。dump 标志会拒绝仅用于启动的标志(`-p`、`--resume`、`--config-replace`)而不是静默忽略它们,`--dump-default-config` 不接受 `--config`。
|
||||
|
||||
Web 和无头界面启动 `base.cordis.yml` 与 `web.cordis.yml`,随后应用 `$DSH_HOME/config.yaml`;显式的 `--config <path>` 会替代该个人覆盖。除此之外,两者共享同一套组合:两者都会告知编码 agent 所用模型和会话工作目录,将调用目录视为默认项目和 Workspace 根目录,除非通过 `--workspace-root <path>` 覆盖,否则会在该根目录下创建具名 Workspace;它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中,渲染预算为 65,536 字节,选用首条消息模型标题,采用与 TUI 相同的有界暂时性模型请求重试策略,并挂载一个可丢弃的内存 SQLite 内容索引服务。Web 还会明确说明交互界面是 DeepSeek Harness Web GUI、当前 checkout 是自身源码位置,并在提示词及受管的 `$DSH_WEB_URL`/`$DSH_WEB_MODE` 中提供该进程的规范本地 URL 和模式;因此,「这个页面」等表述会指向该 GUI,但 agent 不会声称可以访问未显式提供的 DOM、路由或截图状态。在生产模式下,宿主会在下次请求时读取重新构建的前端 dist 和客户端 bundle,因此刷新现有 URL 即可更新该 GUI,无须替换其进程。`dsh web --dev` 会挂载客户端插件的 HMR 接收端,但要实现无刷新更新,还需在同一 checkout 中运行 `pnpm run dev:web`,以监视并重新构建插件 bundle;shell 和普通包(package)的更改仍需重新构建并刷新页面。直接使用裸 `apps/web` Vite 服务会在开始监听前失败,因为它无法注入 `window.__DSH_BOOT__`。索引服务在启动时处于 ACTIVE 状态,但其 `node:sqlite` 模块与数据库句柄分别要到首次内容搜索才会导入和打开。这样可使 Node 22 在尚未使用搜索时的启动输出不出现 SQLite 实验性警告;首次实际搜索仍可能发出运行时警告。每个服务实例独占自己的数据库,因此并行调用既不会共享不受支持的 SQLite 状态,也不会留下派生索引文件,首次搜索还会惰性对账实时日志与持久化日志。无头界面唯一的差异是监听操作系统分配的端口(并行 `dsh -p` 运行绝不冲突;stderr 打印的 URL 会在浏览器中打开实时会话)。两者都需要先构建前端 dist 和客户端 bundle(`pnpm run build && pnpm run build:web`)。
|
||||
|
||||
共享组合把新建 TUI、Web 和无头会话的权限默认设为 `workspace-write` preset(`workspace-write` 文件模式加 `ask` 审批策略)。由沙箱强制约束的 bash 与文件系统修改只能写入会话工作区和平台临时根目录;读取、网络访问和进程可见性不受该策略约束。浏览器可以应答一次性审批请求,并提供 Access 选择器;TUI 提供 `/permission`,但没有审批请求应答者,因此自动请求更宽权限的重试会以拒绝方式关闭,直到用户主动更改会话 preset。`DSH_PERMISSION_MODE` 会更改进程回退值,而「通用」设置中已存储的「权限」值只适用于之后的会话,不会更改已打开的会话。
|
||||
|
||||
三个界面都会使用 `$DSH_HOME/config.yaml`;TUI 和 Web 实时应用有效编辑,而一次性无头运行只在启动时读取。已交付的配置树包含一个空的 `repository-plugins` 配置项,因此独立用户无需 SDK 项目或安装命令,只需配置即可添加已准备的 GitHub 插件:
|
||||
|
||||
```yaml
|
||||
- id: repository-plugins
|
||||
name: '@deepseek-ai/dsh-repository-plugin'
|
||||
config:
|
||||
repositories:
|
||||
- 'github:PolyArch/humanize#<commit>'
|
||||
```
|
||||
|
||||
仓库必须包含已准备的 `.dsh-plugin` 包;[仓库插件契约](../../../packages/cordis/repository-plugin/README.md#standalone-app-configuration)说明创作方式、嵌套插件路径、不可变缓存、信任边界和失败语义。实时编辑失败时,最后一个可用树保持运行,并发出 Cordis 的 HMR 事件 `hmr/config-update-failed`。
|
||||
|
||||
已交付的 TUI 和 Web 组合会注册原生 DeepSeek 适配器,以及 pi-ai 的 OpenAI 和 Anthropic 提供方配置。凭据和端点覆盖来自启动分层环境中的提供方标准变量对:`DEEPSEEK_API_KEY` / `DEEPSEEK_BASE_URL`、`OPENAI_API_KEY` / `OPENAI_BASE_URL` 和 `ANTHROPIC_API_KEY` / `ANTHROPIC_BASE_URL`。
|
||||
|
||||
每个界面也都会注册 `web_search`,且只注册 `web_search`。搜索使用 DeepSeek 的 Anthropic 兼容 Messages 端点,每次调用都会解析同一个 `DEEPSEEK_API_KEY` 凭据引用,并接受独立的 `DEEPSEEK_SEARCH_BASE_URL` 端点覆盖;每次搜索都是一次辅助模型请求,会产生独立的延迟与 token 成本。`web_fetch` 仍处于禁用状态,组合也未挂载默认抓取提供方;需要任意页面抓取能力的部署必须通过覆盖层选择启用。部署决策及其安全边界见[默认 Web 搜索 Agent Note(agent 决策记录)](../../../.agents/notes/implemented/feature/2026-07-31-web-default-search.md)。
|
||||
|
||||
`DSH_TOOLS_MODE` 为整个 Web/无头进程选择工具呈现模式:`native`(未设置时的 schema 默认值)、`code`(仅含 `run_code` 的 Code Mode 线路)或 `both`;任何其他值都会经由 `dsh-tools` 配置 schema 在启动时明确报错。由于 Loader 组合是静态的,该设置作用于整个进程。TUI 界面会忽略该变量并固定为 `native`。
|
||||
|
||||
[`core-web.cordis.yml`](../config/core-web.cordis.yml) 是一个可选启用的 `dsh web --config` 覆盖层:它保留已交付的 Web 宿主、浏览器、Workspace、持久化与权限组合,同时将默认的原生模型界面精简为以所有者为作用域的持久 `bash` 以及 `str_replace_editor`。PTY 后端和编辑器分别消费现有的 Web 沙箱与文件系统提供方。持久 shell 处于打开状态时,会阻止所属会话更改权限模式;因此,在较宽权限下创建的 shell 无法在降权后继续存活。`DSH_TOOLS_MODE` 仍控制由此得到的双工具注册表采用原生/Code Mode 呈现。
|
||||
|
||||
在源码 checkout 中,用以下命令启动这个精简 Web profile:
|
||||
原始 `dsh` 必须提供显式 patch 列表配置:
|
||||
|
||||
```sh
|
||||
pnpm run dsh web --config apps/cli/config/core-web.cordis.yml
|
||||
dsh --config ./app.cordis.yml
|
||||
```
|
||||
|
||||
每个 `dsh` 界面——TUI、Web 与无头——都默认上报会话遥测(该行位于共享的 `base.cordis.yml`):每条会话日志事件以 OTLP/HTTP 日志记录的形式、按 10 秒批处理节奏流向 `https://harness-telemetry.deepseeksvc.com/v1/logs`。`DSH_TELEMETRY_OTLP_URL` 可将 exporter 指向其他 collector;将 `DSH_TELEMETRY_DISABLED` 设为**任意非空值**——包括 `0` 或 `false`——都会在该行加载前将其关停(隐私开关取「宁可误关、不可误开」)。该组合当前未挂载任何脱敏规则:导出记录即原始捕获副本,包含消息正文、工具参数与结果、以及会话工作目录路径。部署口径见 [web-telemetry-default-mount Agent Note](../../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md)。
|
||||
指定文件通过 Include 插件的 patch 算法直接应用到 [`config/base.cordis.yml`](../config/base.cordis.yml) 之上。它不是完整替代树,也不会添加个人 `$DSH_HOME/config.yaml` 或其他 surface overlay。基础配置刻意不包含启动 agent(智能体)或交互前端入口;必填 overlay 负责选择这些部署细节。相对配置路径从调用目录解析。配置解析、schema 校验、模块解析或插件启动失败会得到报告并以非零状态退出。收到 SIGINT 或 SIGTERM 时,挂载的根节点会先 dispose(资源释放)再退出。
|
||||
|
||||
MCP 服务器不是交付默认值,因为默认值必须点名一台服务器:`@deepseek-ai/dsh-mcp-client` 每一行只挂载一台服务器,并把它作为子进程 spawn;该进程不经 `ctx.bash`,因此也不受沙箱策略约束。该包是本 CLI 的运行时依赖,所以已安装的 `dsh` 无需源码检出即可从 `$DSH_HOME/config.yaml` 或 `--config` 覆盖层挂载你自己的服务器:
|
||||
patch 通过 `id` 定位基础配置行,并替换该行完整的 `config` 值,而不是深度合并各键。patch 列表也可插入新行,只要随附 Loader 能解析其插件模块:
|
||||
|
||||
```yaml
|
||||
- insert:
|
||||
- id: mcp-github
|
||||
name: '@deepseek-ai/dsh-mcp-client'
|
||||
config:
|
||||
serverName: github
|
||||
transport: stdio
|
||||
command: npx
|
||||
args: ['-y', '@modelcontextprotocol/server-github']
|
||||
env:
|
||||
GITHUB_TOKEN: !!js process.env.GITHUB_TOKEN
|
||||
- id: agent-loop
|
||||
config:
|
||||
agents:
|
||||
- id: main
|
||||
provider: deepseek-official
|
||||
model: deepseek-v4-flash
|
||||
```
|
||||
|
||||
模型随后会看到 `mcp__github__*`。Streamable HTTP 传输与完整字段表见 [mcp-client README](../../../packages/mcp/mcp-client/README.md)。
|
||||
可在不启动的情况下检查生效的配置树:
|
||||
|
||||
## 安装(开发机)
|
||||
```sh
|
||||
dsh --dump-default-config
|
||||
dsh --config ./app.cordis.yml --dump-config
|
||||
```
|
||||
|
||||
将从源码运行的启动器符号链接到 PATH 上;它通过自身真实路径解析 checkout,因此代码更改会在下次启动时生效,无需构建:
|
||||
`--dump-default-config` 只打印随附基础配置。`--dump-config` 必须与 `--config` 同时使用,并打印基础配置和带来源注释的 overlay。组合使用 `@cordisjs/plugin-include` 的 `applyEntryPatches` 与 `entryListSchema`;`!!js` 表达式保持未求值,找不到目标的 patch 会报告到 stderr。
|
||||
|
||||
## Web 与无头模式
|
||||
|
||||
`dsh web` 启动 `base.cordis.yml` 加 [`config/web.cordis.yml`](../config/web.cordis.yml),并在 `$DSH_HOME/config.yaml` 存在时继续加载它。`dsh web --config <path>` 用显式 patch 列表替代该个人层。`--host`、`--port`、`--workspace-root` 和可重复的 `--trusted-host` 值会成为 Web 宿主 patch;负责这些值的插件 schema 会在启动时验证它们。`--dev` 挂载客户端插件 HMR(热模块替换)接收器;若要无刷新更新客户端 bundle,还需单独运行 `pnpm run dev:web` watcher。
|
||||
|
||||
```sh
|
||||
dsh web
|
||||
dsh web --config ./web-profile.cordis.yml
|
||||
dsh web --dump-default-config
|
||||
dsh web --dump-config
|
||||
```
|
||||
|
||||
生产 Web 运行器需要已构建的包和前端产物(`pnpm run build`)。默认服务地址是 `http://127.0.0.1:3080`。绑定所有接口时,还会信任机器自动发现的 LAN IP 字面量;`--trusted-host` 可添加 `/api` 浏览器信任围栏接受的具名 authority。
|
||||
|
||||
`dsh -p "task"` 使用同一基础配置和 Web 组合,并加载启动时的个人配置;它在 OS 分配的端口上启动 Web 宿主,运行一个新的持久化会话,打印最终答案并退出。它不接受 `--config` 或原始配置 dump flag。
|
||||
|
||||
Web 和无头进程关闭时会给插件树最多 5 秒完成 dispose。第一次 `SIGINT`/`SIGTERM` 启动该优雅排空;第二次信号强制立即退出。如果无头模式正常结束时已经卡在 dispose 中,第一次 `Ctrl+C` 就会升格并立即退出,而不会被吞掉。
|
||||
|
||||
两种模式都将调用目录作为默认 workspace 根目录,以 65,536 字节渲染预算加载适用的 `AGENTS.md` 或 `CLAUDE.md` 指令,并使用内存 SQLite 会话内容索引。Web 监视有效的个人配置编辑;无头模式只在启动时读取该文件。[app-boot 个人配置契约](../../../packages/ui/app-boot/README.md#personal-config)负责配置层优先级、凭据存储、实时更新失败行为和 `$DSH_HOME` 解析。
|
||||
|
||||
新会话默认使用 `workspace-write` 权限预设。Bash 和文件系统修改仅限于会话 workspace 与平台临时根目录;读取、网络访问和进程可见性不受限制。`DSH_PERMISSION_MODE` 更改进程后备值。General settings 中存储的权限影响后续 Web 会话,不改变已打开的会话。
|
||||
|
||||
`DSH_TOOLS_MODE` 为 Web/无头进程选择 `native`、`code` 或 `both`;其他值会导致启动失败。[`config/core-web.cordis.yml`](../config/core-web.cordis.yml) 是可选 Web overlay:它在保留随附宿主、浏览器、workspace、持久化和权限组合的同时,把原生模型 surface 缩减为持久 `bash` 和 `str_replace_editor`。
|
||||
|
||||
## 共享部署行为
|
||||
|
||||
基础配置挂载原生 DeepSeek 适配器、settings 与凭据提供方、稳定的 `web_search`、repository Plugin 支持和会话遥测。提供方凭据存放在 `$DSH_HOME/.env` 或环境中;启动器从不把凭据文件提升到 `process.env`,因此凭据可以轮换。搜索使用 `DEEPSEEK_API_KEY` 并接受 `DEEPSEEK_SEARCH_BASE_URL`;只有 overlay 插入提供方并启用 `web_fetch` 后,该工具才可用。
|
||||
|
||||
会话事件默认作为 OTLP/HTTP 日志流式发送。`DSH_TELEMETRY_OTLP_URL` 选择其他 collector。任何非空 `DSH_TELEMETRY_DISABLED` 都会在启动前禁用遥测配置行。随附基础配置没有遥测脱敏规则,因此导出的记录可能包含消息文本、工具参数与结果以及 workspace 路径;该部署决策由[遥测 Agent Note](../../../.agents/notes/implemented/feature/2026-07-31-web-telemetry-default-mount.md)负责。
|
||||
|
||||
空 `repository-plugins` 行让 Web/无头个人配置和原始 overlay 能够挂载已准备的不可变 repository Plugin generation。参见 [repository Plugin 契约](../../../packages/cordis/repository-plugin/README.md#standalone-app-configuration)。CLI 还随附 `@deepseek-ai/dsh-mcp-client` 作为 overlay 的依赖,但默认不启用 MCP 服务器,因为每条服务器命令都是 agent 沙箱之外的受信任可执行代码。
|
||||
|
||||
## 源码启动器
|
||||
|
||||
把源码运行启动器链接到 PATH:
|
||||
|
||||
```sh
|
||||
ln -sf "$(pwd)/bin/dsh" ~/.local/bin/dsh
|
||||
```
|
||||
|
||||
源码启动会通过 tsx 的 ESM-only hook(`node --import tsx/esm`)运行 `apps/cli/src/bin.ts`,由它转换 TypeScript 并将根 tsconfig 的 `paths` 映射投射到模块解析中。不使用 Node 原生 TypeScript 模式:Node 26 移除了 `--experimental-transform-types`,而 strip-only 模式无法接受源码图依赖的语法(vendor 中的参数属性、装饰器、运行时 enum/namespace)。CJS hook 保持关闭,因为源码图是纯 ESM,而 CJS 解析器会增加约 0.4s 启动耗时。`bin/dsh` 将 `TSX_TSCONFIG_PATH` 固定到 checkout 的根 tsconfig,使解析与 cwd 无关;node-compat 门禁 `dsh-source-launch-smoke` 会在每条受支持的 Node 版本线上运行这一精确启动向量。tsx 应用 `paths` 映射时不检查依赖声明,声明完整性由静态门禁保障:TUI 配置通过 `examples/package.json` 解析裸插件,Web/无头 `cordis.yml` 通过本包的 `dependencies` 解析;`verify-cordis-config` 要求每个已配置的裸插件均已声明,同时允许存在无关依赖。
|
||||
|
||||
`pnpm run dsh` 从仓库根目录运行同一入口并直接转发参数,例如 `pnpm run dsh -p "task"`。构建形式(`lib/bin.js`,通过 `pnpm run build`)会在普通 Node 下启动同一配置。
|
||||
它通过 real path 解析 checkout,并使用 `node --import tsx/esm` 启动 `apps/cli/src/bin.ts`。`TSX_TSCONFIG_PATH` 固定到 checkout 根目录,因此 workspace 包解析不依赖调用目录。`pnpm run dsh` 使用同一入口并转发参数。运行 `pnpm run build` 后,构建形式为 `apps/cli/lib/bin.js`。
|
||||
|
||||
Reference in New Issue
Block a user